core.trainers.grpo.trainer
core.trainers.grpo.trainer
Axolotl GRPO trainers (with and without sequence parallelism handling)
Classes
Name | Description |
---|---|
AxolotlGRPOSequenceParallelTrainer | Extend the base GRPOTrainer for sequence parallelism handling |
AxolotlGRPOTrainer | Extend the base GRPOTrainer for axolotl helpers |
AxolotlGRPOSequenceParallelTrainer
core.trainers.grpo.trainer.AxolotlGRPOSequenceParallelTrainer(
model,
reward_funcs,=None,
args=None,
train_dataset=None,
eval_dataset=None,
processing_class=None,
reward_processing_classes=None,
callbacks=(None, None),
optimizers=None,
peft_config=None,
optimizer_cls_and_kwargs )
Extend the base GRPOTrainer for sequence parallelism handling
Methods
Name | Description |
---|---|
get_train_dataloader | Get dataloader for training |
get_train_dataloader
core.trainers.grpo.trainer.AxolotlGRPOSequenceParallelTrainer.get_train_dataloader( )
Get dataloader for training
AxolotlGRPOTrainer
*args, **kwargs) core.trainers.grpo.trainer.AxolotlGRPOTrainer(
Extend the base GRPOTrainer for axolotl helpers